Investigating Spatial Spillover Effects in Alcohol-Related Driving Crashes

Traffic crash counts have an obvious spatial dimension mainly due to the way they are collected as points in space with reference to location. This necessitates the use of adequate econometric models that duly account for spatial processes (autocorrelation, heterogeneity and most importantly spatial dependence/or correlation) among neighboring spatial units. Failure to account for spatial dependence could lead to the violation of traditional Gauss–Markov assumptions of regression modeling and hence, the resulting estimates could be biased, inconsistent or inefficient. To investigate the hypothesis that spatial processes should be investigated and accounted for when modeling aggregate or macroscopic spatial crash data, this study has found spatial Durbin model (with cross-regressive terms) as the final model specification. This article extends the past research in the domain of highway safety analysis by simultaneously exploring the spatial effects of both sociodemographic and weather factors on alcohol-related driving crash rates. The spatial units of analysis are 1012 townships from a Midwestern state in United States. Alcohol-related driving crashes impose a tremendous social and economic cost on victims and society in general, therefore, generating much concern among agencies and individuals with an interest in public safety. The results may be of interest to groups wanting to reduce alcohol-related crashes and demonstrate the appropriateness of spatial techniques in traffic safety analysis especially for spatially aggregated data.

  • Supplemental Notes:
    • This paper was sponsored by TRB committee ANB50 Standing Committee on Alcohol, Other Drugs, and Transportation.
  • Corporate Authors:

    Transportation Research Board

    ,    
  • Authors:
    • Saeed, Tariq Usman
    • Nateghi, Roshanak
    • Hall, Thomas
    • Waldorf, Brigitte S
  • Conference:
  • Date: 2019

Language

  • English

Media Info

  • Media Type: Digital/other
  • Features: Figures; References; Tables;
  • Pagination: 7p

Subject/Index Terms

Filing Info

  • Accession Number: 01698284
  • Record Type: Publication
  • Report/Paper Numbers: 19-05177
  • Files: TRIS, TRB, ATRI
  • Created Date: Dec 7 2018 9:50AM